by Tianjun Liao, Marco A. Montes de Oca,
Dogan Aydin, Thomas Stützle
and Marco Dorigo
April 2011
| Submitted to GECCO 2011. [the best paper award in ACO-SI track] |
ACOr is one of the most popular ant colony optimization algorithms for tackling continuous optimization problems. In this paper, we propose IACOr-LS, which is a variant of ACOr that uses local search and that features a growing solution archive. We experiment with Powell's conjugate directions set, Powell's BOBYQA, and Lin-Yu Tseng's Mtsls1 methods as local search procedures. Automatic parameter tuning results show that IACOr-LS with Mtsls1 (IACOr-Mtsls1) is not only a signi cant improvement over ACOr, but that it is also competitive with the state-of-theart algorithms described in a recent special issue of the Soft Computing journal. Further experimentation with IACOr- Mtsls1 on an extended benchmark functions suite, which includes functions from both the special issue of Soft Computing and the IEEE 2005 Congress on Evolutionary Computation, demonstrates its good performance on continuous optimization problems.
Keywords: Ant Colony Optimization, Continuous Optimization, Local
Search, Automatic Parameter Tuning
| Performance on 19 SOCO functions of
100 dimentions
|
|---|
| Comparison of ACOr with 16
algorithms in SOCO on 19 functions of 100 dimensions
|
|---|
| Comparison of IACOr-Mtsls1 on 19 functions of 50 dimensions(median)
|
|---|
| Comparison of IACOr-Mtsls1 on 19 functions of 50 dimensions(mean)
|
|---|
| Comparison of IACOr-Mtsls1 on 19 functions of 100 dimensions(median)
|
|---|
| Comparison of IACOr-Mtsls1 on 19 functions of 100 dimensions(mean)
|
|---|
